DETAILED ACTION
Notice to Applicant
1. The following is a FINAL Office action upon examination of application number 19/113,935 filed on 03/21/2025. Claims 1-20 are pending in this application, and have been examined on the merits discussed below.
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
3. Application 19/113,935 filed 03/21/2025 is a National Stage entry of PCT/US2023/033497, International Filing Date: 09/22/2023. Application 19/113,935 claims Priority from Provisional Application 63/409,112, filed 09/22/2022.
Response to Amendment
4. In the response filed May 18, 2026, Applicant amended claims 1-5, 8-12, 15-17, and 19, and did not cancel any claims. No new claims were presented for examination.
5. Applicant's amendments to claims 1 and 3 are hereby acknowledged. The amendments are sufficient to overcome the previously issued objections; accordingly, these objections have been removed.
6. Applicant's amendments to claims 1, 3-4, 8, and 15 are hereby acknowledged. The amendments are sufficient to overcome the previously issued rejection of claims 1-20 under 35 U.S.C. 112(b); accordingly, this rejection has been withdrawn. However, a new rejection under 35 U.S.C. 112(b) is presented in light of the claim amendments.
7. Applicant's amendments to claims 1, 8, and 15 are hereby acknowledged. The amendments are sufficient to overcome the previously issued claim rejection under 35 U.S.C. 101; accordingly, this rejection has been withdrawn.
Response to Arguments
8. Applicant's arguments filed May 18, 2026, have been fully considered.
9. Applicant submits “As noted in the above-referenced interview, the Examiner indicated that the amended limitation "controlling oilfield equipment based on the ranking of each of the predicted economic outcomes by transmitting control instructions to the oilfield equipment to implement an intervention at the candidate wells" as recited by amended claims 1, 8, and 15 likely overcomes the rejection under 35 U.S.C. § 101. Without acquiescing to the merits of the rejection, Applicant presently amends independent claims 1, 8, and 15 accordingly. Applicant respectfully submits that the claims as amended are patent eligible for at least the reasons set forth below.” [Applicant’s Remarks, 05/18/2026, page 11]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
10. Applicant submits “In the Office Action, the Examiner alleged that claims 1-20 are directed to an abstract idea falling within the "Mental Processes" grouping because the steps "may be accomplished by human judgment or evaluation, such as with the aid of pen and paper." See Office Action, p. 6. Applicant respectfully disagrees.” [Applicant’s Remarks, 05/18/2026, page 12]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
11. Applicant submits “that the claims as amended recite specific technical operations that cannot practically be performed in the human mind. In particular, amended claims 1, 8, and 15 recite that the second machine learning model "generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in- place map." This limitation requires creating hundreds of computational realizations through systematic parameterization of property values-varying them above and below the values provided by the first machine learning model-to produce probabilistic scenario distributions and stochastic maps. See As-Filed Specification, paragraphs [0058] and [0082]. These computationally intensive operations involving probabilistic analysis across multiple well sites and pay zones go far beyond what any human could perform mentally or with pen and paper.” [Applicant’s Remarks, 05/18/2026, page 12]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
12. Applicant submits “ Furthermore, the amended claims recite that "the missing reserves comprise behind casing opportunities (BCOs) identified based upon a quality trust factor exceeding a quality trust factor threshold." This is a specific technical criterion for identifying BCOs that requires computational evaluation of log data quality against a defined threshold. See As-Filed Specification, paragraphs [0054]-[0056] (describing how "if the quality trust factor is high the model uses that information, to flag or identify hydrocarbon intervals behind casing" and "In the case of the low-quality trust factor, the model uses its own machine learning prediction module for the property prediction of the interval"). This threshold-based determination is a technical operation performed by the machine learning model-not a vague mental judgment that could be performed with pen and paper.” [Applicant’s Remarks, 05/18/2026, pages 12-13]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
13. Applicant submits “Moreover, the specific combination, sequence, and interaction of the four machine learning models provides a technical solution to a technical problem in reservoir engineering. The claims do not merely automate a manual process; rather, they recite a specific technical pipeline where: (1) a first machine learning model generates reservoir quality indicators from well logs; (2) a second machine learning model uses those indicators to determine missing reserves including BCOs based on a quality trust factor threshold, and generates probabilistic realizations and stochastic maps; (3) a third machine learning model determines candidate wells based on the missing reserves; and (4) a fourth machine learning model predicts economic outcomes for intervention options. This ordered combination of machine learning models, each building upon the outputs of the previous model, represents a specific technical architecture that addresses the technical problem of identifying missing reserves in a reservoir more quickly and accurately than traditional methods. See As-Filed Specification, paragraph [0093].” [Applicant’s Remarks, 05/18/2026, page 13]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
14. Applicant submits “Assuming, arguendo, that the claims recite a judicial exception (e.g., mental process and/or certain methods of organizing human activity, as contended by the Examiner), Applicant submits that the claims "integrate[ the recited judicial exception into a practical application of that exception." MPEP § 2106.04(II)(A)(2). In the Office Action, the Examiner indicated that the claims do not integrate the allegedly abstract idea into a practical application. Office Action, pages 6-7. Applicant respectfully disagrees.” [Applicant’s Remarks, 05/18/2026, pages 13-14]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
15. Applicant submits “that the additional elements included in claims 1-20 perform specific technical operations. For example, amended claims 1, 8, and 15 recite "controlling oilfield equipment based on the ranking of each of the predicted economic outcomes by transmitting control instructions to the oilfield equipment to implement an intervention at the candidate wells." This limitation is not merely making a decision or performing an abstract analysis. Rather, it requires transmitting control instructions to physical oilfield equipment to implement an actual intervention at the candidate wells. See As-Filed Specification, paragraphs [0021]-[0022] and [0040] (describing control of oilfield operations). The current claim features apply machine learning-generated predictions to effect a real-world change in oilfield operations, constituting a meaningful limitation that integrates any alleged abstract idea into a practical application.” [Applicant’s Remarks, 05/18/2026, page 14]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
16. Applicant submits “that the claims recite an inventive concept under Step 2B and are directed to patentable subject matter.” [Applicant’s Remarks, 05/18/2026, page 15]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
17. Applicant submits “that the recited features of independent claims 1, 8, and 15 add specific limitations to the claim that are not well-understood, routine, or conventional activity in the field. In particular, the quality trust factor threshold for identifying BCOs represents a specific technical approach to evaluating log data quality before using it to identify behind casing opportunities.” [Applicant’s Remarks, 05/18/2026, page 15]
In response to Applicant’s argument, it is noted that the claim amendments are sufficient to overcome the previously issued claim rejections under 35 U.S.C.101; accordingly, these rejections have been withdrawn.
18. Applicant submits “The ordered combination of these elements-four distinct machine learning models operating in a pipeline, with the second model generating probabilistic realizations and stochastic maps based on quality trust factor thresholds, and the results being used to transmit control instructions to oilfield equipment-represents significantly more than any alleged abstract idea. This combination provides a technological improvement over prior methods for identifying missing reserves, not merely the application of generic computing to an abstract idea.” [Applicant’s Remarks, 05/18/2026, page 16]
19. Applicant submits “Benhallam does not teach or suggest identifying BCOs "based upon a quality trust factor exceeding a quality trust factor threshold" as recited by amended claims 1, 8, and 15.” [Applicant’s Remarks, 05/18/2026, page 17]
In response to the Applicant’s argument that “Benhallam does not teach or suggest identifying BCOs "based upon a quality trust factor exceeding a quality trust factor threshold" as recited by amended claims 1, 8, and 15,” the Examiner notes the limitations being argued by Applicant as being newly amended to the claims in the response filed 05/18/2026, which have been addressed in the updated rejection below. Applicant’s argument has been considered, but it pertains to amendments to independent claims 1, 8, and 15 that are believed to be addressed via the updated ground of rejection under §103 set forth in the instant Office action, which incorporates a new reference and new citations to address the amended limitations in claim and supports a conclusion of obviousness of the amended claims.
20. Applicant submits “With respect to the limitation "wherein the second machine learning model generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in-place map," none of the cited references teaches or suggests this feature.” [Applicant’s Remarks, 05/18/2026, page 18]
In response to the Applicant’s argument that none of the cited references teaches or suggests “wherein the second machine learning model generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in-place map,” the Examiner notes the limitations being argued by Applicant as being newly amended to the claims in the response filed 05/18/2026, which have been addressed in the updated rejection below. Applicant’s argument has been considered, but it pertains to amendments to independent claim 1 that are believed to be addressed via the updated ground of rejection under §103 set forth in the instant Office action, which incorporates a new reference and new citations to address the amended limitations in claim and supports a conclusion of obviousness of the amended claims.
21. Applicant submits “claim 1 recites, inter alia, "predicting, by a fourth machine learning model, economic outcomes for a plurality of intervention options for the candidate wells" and "controlling oilfield equipment based on the ranking of each of the predicted economic outcomes by transmitting control instructions to the oilfield equipment to implement an intervention at the candidate wells." None of the cited references teaches or suggests these features.” [Applicant’s Remarks, 05/18/2026, page 18]
In response to the Applicant’s argument that none of the cited references teaches or suggests “"predicting, by a fourth machine learning model, economic outcomes for a plurality of intervention options for the candidate wells” and “controlling oilfield equipment based on the ranking of each of the predicted economic outcomes by transmitting control instructions to the oilfield equipment to implement an intervention at the candidate wells,” the Examiner notes the limitations being argued by Applicant as being newly amended to the claims in the response filed 05/18/2026, which have been addressed in the updated rejection below. Applicant’s argument has been considered, but it pertains to amendments to independent claim 1 that are believed to be addressed via the updated ground of rejection under §103 set forth in the instant Office action, which incorporates a new reference and new citations to address the amended limitations in claim and supports a conclusion of obviousness of the amended claims.
22. Applicant’s remaining arguments either logically depend from the above-rejected arguments, in which case they too are unpersuasive for the reasons set forth above, or they are directed to features which have been newly added via amendment. Therefore, this is now the Examiner's first opportunity to consider these limitations and as such any arguments regarding these limitations would be inappropriate since they have not yet been examined. A full rejection of these limitations will be presented later in this Office Action.
Claim Rejections - 35 USC § 112
23. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
24. Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
25. Claims 1, 8, and 15 were amended to recite the phrase “wherein the second machine learning model generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in-place map.” This phrase is unclear because the claim does not identify what “values” are provided by the first machine learning model. The first machine learning model is recited as generating a plurality of reservoir quality indicators, but the relationship between those reservoir quality indicators and the subsequently recited “values” is not explained. It is unclear what values are being varied or parametrized by the second machine learning model, therefore rendering the claims indefinite. Appropriate correction is required.
26. All claims dependent from above rejected claims are also rejected due to dependency.
Claim Rejections - 35 USC § 103
27. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
28. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
29. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
30. This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
31. Claims 1-3, 5-10, 12-17, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Benhallam et al., Pub. No.: US 2019/0325331 A1, [hereinafter Benhallam], in view of Bardy et al., Pub. No.: US 2021/0222518 A1, [hereinafter Bardy], in further view of Tawil et al., Pub. No.: US 2021/0317726 A1, [hereinafter Tawil].
As per claim 1, Benhallam teaches a method for identifying missing reserves in a reservoir (paragraphs 0005, 0069, 0132), the method comprising:
ingesting a plurality of logs of well site data for a plurality of well sites in the reservoir (paragraph 0005, discussing identifying and implementing hydrocarbon production opportunities including recompletion opportunities, new vertical drill target opportunities, and horizontal or deviated well target opportunities. In one embodiment, a computer system accesses petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site. The computer system also accesses historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals that represent material remaining in hydrocarbon wells on the hydrocarbon site; paragraph 0007, discussing that the computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify grid regions in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints; paragraph 0033, discussing that computer system accesses petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site; paragraph 0038, discussing that the computer system also includes a drainage analyzer configured to identify zones of the hydrocarbon extraction site that include drained portions that have been drained by existing wells on the site; paragraph 0110, discussing that the method includes accessing one or more portions of petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site. For example, the data accessing module may access petrophysical log data obtained at hydrocarbon extraction site; paragraphs 0008, 0035, 0065, 0129);
generating, by a first machine learning model, a plurality of reservoir quality indicators for a plurality of well sites from the plurality of logs (paragraph 0005, discussing identifying and implementing hydrocarbon production opportunities including recompletion opportunities, new vertical drill target opportunities, and horizontal or deviated well target opportunities; paragraph 0006, discussing that the computer system forecasts, using statistical characterization methods and machine learning algorithms, projected production results for recompletion opportunities at the hydrocarbon site. The projected production results include initial production estimates and/or ultimate recovery estimates. The computer system calculates a level of geologic uncertainty relative to the forecasted production results and determined drainage...; paragraph 0008, discussing that the computer system then produces a list of new vertical drilling prospects for selection according to geological likelihood, operational constraints and/or reservoir management factors, and, at least in some embodiments, initiates hydrocarbon production at the selected new vertical drilling opportunity; paragraph 0008, discussing that a computer system is provided for identifying horizontal or deviated well target opportunities. The computer system includes a data accessing module configured to access geological, petrophysical or engineering data related to a hydrocarbon extraction site; paragraph 0036, discussing that the computer system also estimates the probability of exceeding or falling short of the forecasted potential production rate using at least a portion of neighborhood production data indicating an amount that wells in neighboring zones are producing, and determines, based on geologic factors related to the hydrocarbon site, a geologic risk measurement for a given target opportunity. The risk measurement incorporates the heterogeneity of the reservoir and the quality of the geological modeling work. The computer system then filters a list of new vertical drilling opportunities for selection according to geological feasibility, operational constraints, and/or engineering feasibility, and initiates hydrocarbon production at the selected new vertical drilling opportunity; paragraph 0057, discussing identifying various remaining, feasible, and actionable field development opportunities. These include recompletion behind-pipe opportunities, vertical new drill locations, sidetrack opportunities, and optimal deviated/horizontal targets…; paragraph 0065, discussing a production forecast module that forecasts production for behind-pipe opportunities using various methods outlined below; paragraph 0069, discussing that behind-pipe opportunities refer to target intervals that contain unswept oil in existing wells, which require additional recompletions for production…; paragraph 0084, discussing that zone RPOS (relative probability of success) map represents the aggregate of the normalized input attribute maps. A global RPOS map is created by combining trends in the individual zone RPOS maps. Since the individual zone RPOS maps were created using globally normalized input attribute maps, the global RPOS average map will weigh every zone appropriately, and will essentially reflect the aggregate quality from all the zones at any given location. The global RPOS map is used together with the spacing grid to identify locations that maximize RPOS while honoring the spacing grid constraints; paragraph 0122, discussing that the geologic uncertainty calculation module determines based on geologic factors related to the hydrocarbon site, a geologic risk measurement for a given target opportunity. The risk measurement indicates the heterogeneity of the reservoir and the quality of the geological distribution. The filtering module then filters a list of new vertical drilling opportunities for selection according to geological feasibility, operational constraints and/or engineering feasibility, and upon the well target identifier selecting one of the feasible wells (and potentially the most feasible well), hydrocarbon production is initiated at the selected new vertical drilling opportunity by sending the signal);
determining, by a second machine learning model, the missing reserves based on the plurality of reservoir quality indicators for the plurality of well sites, wherein the missing reserves comprise behind casing opportunities (BCOs) identified (paragraph 0033, discussing that the computer system also accesses historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals that represent material remaining in hydrocarbon wells on the hydrocarbon site; paragraph 0034, discussing that the computer system forecasts, using statistical characterization methods and machine learning algorithms, projected production results for recompletion opportunities at the hydrocarbon site. The projected production results include initial production estimates and/or ultimate recovery estimates. The computer system calculates a level of geologic uncertainty relative to the forecasted production results and determined drainage, where the geologic uncertainty levels indicate levels of risk; paragraph 0057, discussing a fully automated platform that applies advanced computational algorithms and data mining techniques on multi-disciplinary datasets to identify various remaining, feasible, and actionable field development opportunities. These include recompletion behind-pipe opportunities, vertical new drill locations, sidetrack opportunities, and optimal deviated/horizontal targets. The platform can also be used to identify custom types of opportunities such as reactivation opportunities; paragraph 0070, discussing that a drained net pay (DNP) log may be created in each well using an algorithm that incorporates the most recent completion data together with a net pay log reflecting various petrophysical cutoffs (e.g. porosity, permeability, water saturation, etc.). The algorithm tracks each net pay interval that is in direct or indirect communication with existing perforations. This tracking can also be customized to account for flow barriers (i.e. baffles). The characteristic attributes of what constitutes a baffle layer are provided by the user. For example, a pay interval that is separated from an existing perforation by a baffle will not be tracked or considered drained by the algorithm. The remaining pay that is not part of the DNP intervals is classified as uncontacted net pay (UNP); paragraph 0074, discussing that small DIs (drainage index) reflect areas where only thin sand layers have been accessed or drained, and therefore have more oil remaining in either overlying or underlying sand packages; paragraph 0110, discussing that the data accessing module may also access historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals. These uncontacted net pay intervals represent material remaining in hydrocarbon wells on the hydrocarbon site. As noted above, many wells are initially mined for a period of time, and when mining becomes economically unfeasible, the mining equipment is moved to more profitable wells. Thus, existing wells may still have uncontacted material in them; paragraphs 0058, 0069, 0083, 0111, 0112);
determining, by a third machine learning model, candidate wells based on the missing reserves (paragraph 0007, discussing that a computer system identifies new vertical drill target opportunities. The computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify grid regions in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints. The computer system then generates a relative probability of success (RPOS) mapping for each zone that ranks the identified regions according to zone-mappable attributes associated with productive hydrocarbon wells, and further forecasts, for each new drill location, a potential production rate for one or more target zones; paragraph 0008, discussing that the computer system further includes a domain identifier configured to identify potential regions that satisfy stratigraphic, spatial and depth constraints within the hydrocarbon extraction site, as well as a spatial analyzer configured to perform a 3D spatial analysis of the identified potential well placement zones within the hydrocarbon extraction site; paragraph 0010, discussing that part of the computer system are an optimization module configured to perform an interference analysis designed to select an optimal set of non-interfering well candidates…; paragraph 0038, discussing that part of the computer system are an optimization module configured to perform an interference analysis designed to filter through and select an optimal set of non-interfering well candidates, a forecasting module configured to forecast an initial production rate for the selected horizontal well placement candidate placed in the identified location on the hydrocarbon extraction site using analytical, simulation, or machine learning models, and a production initiator configured to initiate hydrocarbon production at the selected horizontal well placement candidate in the identified location; paragraph 0096, discussing statistical methods that leverage spatial and temporal neighborhood fluid data, machine learning techniques like supervised neural networks, analytical models specifically designed for horizontal wells, and simulation models. Step 1206 selects the best set of non-interfering candidates that optimize a given objective function; paragraphs 0081, 0085, 0113, 0119);
predicting, by a fourth machine learning model, outcomes for a plurality of intervention options for the candidate wells (paragraph 0006, discussing that the computer system also filters a list of recompletion opportunities [i.e., plurality of intervention options] for selection according to geological feasibility, mechanical feasibility and/or engineering feasibility, and, at least in some embodiments, initiates hydrocarbon production at the recompletion opportunity; paragraph 0036, discussing that the computer system then filters a list of new vertical drilling opportunities for selection according to geological feasibility, operational constraints, and/or engineering feasibility, and initiates hydrocarbon production at the selected new vertical drilling opportunity; paragraph 0056, discussing methods and systems provided for identifying recompletion, new and horizontal well target opportunities; paragraph 0112, discussing that the method next includes forecasting, using statistical neighborhood methods and one or more machine learning algorithms, projected production results for one or more recompletion opportunities at the hydrocarbon site, the projected production results including initial production estimates and/or ultimate recovery estimates. The forecasting module of computer system may use statistical neighborhood methods and/or machine learning algorithms to forecast projected production results. These projected results may indicate how much remaining material is likely to be produced during an initial term (i.e. initial production estimate) and over the life of the well (i.e. ultimate recovery estimate); paragraph 0114, discussing that the method next includes filtering a list of recompletion opportunities for selection according to geological feasibility, mechanical feasibility and/or engineering feasibility. The filtering module of computer system may filter a list of target recompletion opportunities that are available within a given hydrocarbon extraction site…The filtering module may sort through possible recompletion opportunities to identify those that best match a given location. Once a recompletion opportunity has been identified by the well target identifier, the computer system sends a signal to initiate production at that well. Further commands may also be sent controlling how the oil is produced. Indeed, in at least some embodiments, controls from the computer system directly control equipment and/or processes at the hydrocarbon extraction site; paragraph 0121);
ranking each of the plurality of intervention options for the candidate wells based upon the predicted outcomes (paragraph 0007, discussing that the computer system then generates a relative probability of success (RPOS) mapping for each zone that ranks the identified regions according to zone-mappable attributes associated with productive hydrocarbon wells, and further forecasts, for each new drill location, a potential production rate for one or more target zones; paragraph 0010, discussing ranking the identified zones of the site according to zone-mappable attributes associated with productive hydrocarbon wells; paragraph 0114, discussing that The filtering module may sort through possible recompletion opportunities to identify those that best match a given location; paragraph 0128, discussing that the probability of success calculation module generates a relative probability of success (RPOS) 3D map that ranks the identified zones of the site (in ranking) according to zone-mappable attributes associated with productive hydrocarbon wells); and
controlling oilfield equipment based on the ranking of each of the predicted economic outcomes by transmitting control instructions to the oilfield equipment to implement an intervention at the candidate wells (paragraph 0006, discussing that the computer system also filters a list of recompletion opportunities for selection according to geological feasibility, mechanical feasibility and/or engineering feasibility, and, at least in some embodiments, initiates hydrocarbon production at the recompletion opportunity; paragraph 0114, discussing that the filtering module may sort through possible recompletion opportunities to identify those that best match a given location. Once a recompletion opportunity has been identified by the well target identifier, the computer system sends a signal to initiate production at that well. Further commands may also be sent controlling how the oil is produced. Indeed, in at least some embodiments, controls from the computer system directly control equipment and/or processes at the hydrocarbon extraction; paragraph 0130, discussing that initiating hydrocarbon production at the selected horizontal well in the identified location may include providing control instructions that direct operation of the selected target. This could include controlling equipment, computing systems, sensors, electronics or other devices or systems).
While Benhallam describes determining whether it would be economically profitable to place a rig at a given well (paragraph 0111), Benhallam does not explicitly teach wherein the missing reserves comprise behind casing opportunities (BCOs) identified based upon a quality trust factor exceeding a quality trust factor threshold, and wherein the second machine learning model generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in-place map; predicting, by a fourth machine learning model, economic outcomes for a plurality of intervention options for the candidate wells; and controlling oilfield equipment based on the ranking of each of the predicted economic outcomes. Bardy in the analogous art of wellbore planning systems teaches:
predicting, by a fourth machine learning model, economic outcomes for a plurality of intervention options for the candidate wells (paragraph 0009, discussing that a well-placement optimization procedure can find the best well configuration given various subterranean formation and reservoir parameters. A well configuration can include well placement or location and well geometry, including a projected three-dimensional drill path within the subterranean formation to reach the reservoir. A best well configuration can be used to maximize the hydrocarbon recovery from a reservoir. Well placement optimization techniques can use parameters such as porosity field, permeability field, well cost, and fluid properties, which can be combined with an objective function to be assign weights to each well configuration; paragraph 0014, discussing that enabling determination of the hydraulic fracture propagation potential and then the corresponding hydrocarbon recovery using a numerical flow simulator. The best configuration for a given number of wells can be identified; paragraph 0029, discussing that the memory can include a Planning Engine, which can include instructions to perform operations for selecting and outputting a well placement plan for a wellbore in an area; paragraph 0048, discussing that a well placement plan for a well in the region is selected using projected hydrocarbon recovery rates from the well configuration models. The well optimization system can use the projected hydrocarbon recovery rates determined to determine and select an optimized well placement plan. The well placement plan can include a well location with respect to the local area in the region, a well geometry describing how the wellbore is designed to permeate the subterranean formation, and other wellbore parameters used for drilling and production phases; paragraph 0049, discussing that a machine-learning model can be used to select the well placement plan. A teaching set can be generated using the projected hydrocarbon recovery rates and the well configuration models. A machine-learning model can be taught using the teaching set. The machine-learning model can be configured to output hydrocarbon recovery rates corresponding to each of the well configuration models. The well configuration models can be analyzed using an optimizer and the machine-learning model to determine a well placement plan having a highest projected hydrocarbon recovery rate. In some examples, selecting the well placement plan can include building a response surface using the projected hydrocarbon recovery rates and the well configuration models, and analyzing the response surface using a minimization algorithm to determine the well placement plan having a highest projected hydrocarbon recovery rate; paragraph 0067, discussing that a best well configuration is determined using the machine-learning model and an optimizer. The well optimization system can include an optimizer. The well optimization system can input the projected hydrocarbon recovery rates and the well configuration models into the optimizer to determine which of the projected hydrocarbon recovery rates and well configuration models can maximize recovery for a given reservoir. The optimizer can input parameters specific to the reservoir targeted for optimization into the machine-learning model, and the machine-learning model may output multiple available well configuration models, each with projected hydrocarbon recovery rates. The optimizer can be configured to choose the most suitable well configuration model from the available well configuration models based on the projected hydrocarbon recovery rates output by the machine-learning model, in addition to other factors, such as well cost, well integrity, production time, and other factors important in achieving efficient well operations. The optimizer can define these well factors to determine which of the well configurations can produce the maximum amount of hydrocarbons while simultaneously adhering to user-defined physical constraints; paragraph 0069, discussing that the machine-learning model can be taught to produce more accurate results with respect to a specific application); and
controlling oilfield equipment based on the ranking of each of the predicted economic outcomes (paragraph 0050, discussing that the well placement plan that is selected is output. The well placement plan can be used to plan one or more wellbores in the region. The well placement plan can be generated by the well optimization system that can output the well placement plan to a display device or to other devices. In some examples, the well optimization system can output the well placement plan to a user for implementation of the plan in an actual well planning and drilling environment; paragraph 0052, discussing that the well optimization system can cause a well tool setting, wellbore characteristic, or both to be adjusted in order to manipulate the drill string, drill bit, wireline tool, or other downhole device; paragraph 0067, discussing that a best well configuration is determined using the machine-learning model and an optimizer. The well optimization system can include an optimizer. The well optimization system can input the projected hydrocarbon recovery rates and the well configuration models into the optimizer to determine which of the projected hydrocarbon recovery rates and well configuration models can maximize recovery for a given reservoir. The optimizer can input parameters specific to the reservoir targeted for optimization into the machine-learning model, and the machine-learning model may output multiple available well configuration models, each with projected hydrocarbon recovery rates. The optimizer can be configured to choose the most suitable well configuration model from the available well configuration models based on the projected hydrocarbon recovery rates output by the machine-learning model, in addition to other factors, such as well cost, well integrity, production time, and other factors important in achieving efficient well operations. The optimizer can define these well factors to determine which of the well configurations can produce the maximum amount of hydrocarbons while simultaneously adhering to user-defined physical constraints; paragraph 0087, discussing determining a projected hydrocarbon recovery rate by simulating flow with the new hydraulic fractures; select a well placement plan for a well in the region using a plurality of projected hydrocarbon recovery rates from the plurality of well configuration models; and output the well placement plan that is selected and that is usable to plan one or more wellbores in the region; paragraph 0051).
Benhallam is directed towards a method and system for identifying and implementing hydrocarbon production opportunities. Bardy relates generally to a wellbore environment for extracting hydrocarbons. Therefore they are deemed to be analogous as they both are directed towards solutions for wellbore operations management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Benhallam with Bardy because the references are analogous art because they are both directed to solutions for oilfield reservoir and production analysis, which falls within applicant’s field of endeavor (reservoir planning and management), and because modifying Benhallam to include Bardy’s features for predicting, by a fourth machine learning model, economic outcomes for a plurality of intervention options for the candidate wells, and controlling oilfield equipment based on the ranking of each of the predicted economic outcomes, in the manner claimed, would serve the motivation of optimizing a well configuration for a new reservoir or currently producing reservoir to produce a variety of benefits with respect to overall well production efficiency, integrity, and safety (Bardy at paragraph 0012); and further obvious because the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
The Benhallam-Bardy combination does not explicitly teach wherein the missing reserves comprise behind casing opportunities (BCOs) identified based upon a quality trust factor exceeding a quality trust factor threshold, and wherein the second machine learning model generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in-place map. However, Tawil in the analogous art of wellsite planning systems teaches these concepts. Tawil teaches:
wherein the missing reserves comprise behind casing opportunities (BCOs) identified based upon a quality trust factor exceeding a quality trust factor threshold (paragraph 0093, discussing that the WPO (well planning optimization) module is configured to optimize and automate an example well planning process. A workflow process executed using the WPO module includes capturing and exploiting information that indicates uncertainty of reservoir properties to ensure maximum reservoir contact during a drilling operation. In some implementations, the uncertainty information is based on probabilistic modeling of reservoir quality relative to sediments and rocks of the reservoir, coupled with computed risk estimations of contacting low quality sediments. In some implementations, the uncertainty information is quantified in the form of a multi-dimensional risk volume or risk map that is based on probabilistic modeling using some or all of the geological, petrophysical, geophysical, and dynamic engineering data in the system; paragraph 0135, discussing that the datasets stored can also include at least a portion of the information pertaining to oil and gas reserves. In some examples, the information pertaining to oil and gas reserves describes various known or suspected locations for obtaining trapped hydrocarbon accumulations. The information can be used to predict some (or all) geological-related factors to bring the hydrocarbons (oil and gas) to the surface at optimum or threshold cost. The economic datasets includes data describing economically producible hydrocarbons. In some implementations, the data of the economic datasets that describes the economically producible hydrocarbons is based on different sets of information pertaining to oil and gas reserves; paragraph 0165, discussing that the geo-steering application uses the adjusted (or updated) predictive and analytical capabilities of the geological model to generate a new drilling plan. The new drilling plan can be based on predictions about geological-related factors for accurately locating trapped hydrocarbon accumulations. For example, the new drilling plan can be based on detailed prediction of about subsurface properties such as rock porosity, permeability, hydrocarbon distribution, and water saturation at each discrete element of a reservoir. The new drilling plan and bring the hydrocarbons (oil and gas) to the surface within a threshold cost or economic production metric; paragraph 0175, discussing that the well planning application computes predictions about formation top/logs. For example, the predictions about formation top/logs are computed with respect to the target reservoir. The well planning application generates geological maps and cross sections for one or more areas of interest based on data describing the location parameters of a targeted reservoir. The well planning application produces various types of assessment documents that are related to approving or disapproving of a particular well plan. For example, the well planning application can process information derived from probabilistic models WPO module to determine uncertainties relating to properties of the targeted reservoir. The well planning application can reference uncertainties derived from the probabilistic model to determine planning parameters (numerical parameters), including preferred geographic locations and resources that are required for a well plan to meet or exceed an example approval threshold; paragraph 0179, discussing that the WPO application receives input data in response to an event-driven trigger and determines a target area and well parameters based on the input data. The WPO application includes optimization methods that involve processing and analysis of 1D, 2D, and 3D geological models. For example, the WPO application is based on probabilistic multi-dimensional modeling of reservoir quality with data describing risk estimations relating to the reservoir), and
wherein the second machine learning model generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in-place map (paragraph 0038, discussing that the probabilistic models and risk maps are used to compute estimates of hydrocarbon reserves at the particular area of a reservoir in the region; paragraph 0047, discussing that the computing device includes a machine-learning engine (“ML engine”) that is configured to process input data to generate one or more predictive models…; paragraph 0099, discussing that the reservoir optimization module is operable to provide a graphical user interface that enables the users to construct testing scenarios and provide user input for a scenario via the graphical interface. In some implementations, the user input defines testing parameters for evaluating a scenario against a particular reservoir model; paragraph 0101, discussing that the reservoir optimization module can receive input data along with a request (that is, a user request) to test or evaluate a reservoir model against a particular scenario. The input data can include location parameters for a subsurface area of interest and information identifying a targeted reservoir in the area of interest; paragraph 0125, discussing that the model captures the newly incoming data irrespective of whether the data are applied per area, per field, or per reservoir. The earth model selects one or more workflows that enable the model to obtain optimal results, such as results that have the lowest quantified uncertainty; paragraph 0134, discussing that the optimization approach can include processing parameters, including parameter values, of a dataset generated during a well drilling operation. The optimization approach can also include detecting certain missing and abnormal parameters or parameter values corresponding to a well bore and properties of geological layers along the drilling trajectory. The approach may further include performing one or more mathematical processes, such as data imputation, to predict different parameters and parameter values that correspond to the drilling operation so as to optimize the generated dataset; paragraph 0135, discussing that the datasets can also include at least a portion of the information pertaining to oil and gas reserves. In some examples, the information pertaining to oil and gas reserves describes various known or suspected locations for obtaining trapped hydrocarbon accumulations; paragraph 0175, discussing that the well planning application can process information derived from probabilistic models WPO module to determine uncertainties relating to properties of the targeted reservoir. The well planning application can reference uncertainties derived from the probabilistic model to determine planning parameters (numerical parameters), including preferred geographic locations and resources that are required for a well plan to meet or exceed an example approval threshold; paragraph 0180, discussing that based on the geological models, the WPO (well planning optimization) application is operable to generate one or more risk models. For example, the WPO application is configured to model, in a 3D/multi-dimensional space, the risk of encountering poor quality reservoir rocks. In some implementations, the risk estimations are modeled in 3D by defining geological, geophysical, petrophysical, and reservoir engineering data constraints. One or more risk models of the WPO application are operable to generate one or more risk maps that are used to compute estimates of hydrocarbon reserves at particular areas of a reservoir in a given region. For example, the risk models can generate a porosity only risk map, a facies only risk map, and a porosity and facies risk map. In some implementations, the WPO application includes risk models that are operable to generate a petrophysical & seismic AI risk map; paragraph 0187, discussing that the system generates a risk map that is used to estimate a probability of contacting a particular area of the reservoir. For example, the system is operable to use the integrated multi-dimensional geological model to generate the risk map in response to modeling properties of the reservoir. The risk map is configured to estimate probabilities that represent a predicted likelihood of contacting a particular area of the reservoir that has properties corresponding to at least one of the modeled properties; paragraphs 0093, 0174).
The Benhallam-Bardy combination describes features related to wellbore planning and implementing hydrocarbon production opportunities. Tawil relates to techniques for allocating resources for implementing a well-planning process. Therefore they are deemed to be analogous as they both are directed towards solutions for wellbore operations management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Benhallam-Bardy combination with Tawil because the references are analogous art because they are both directed to solutions for oilfield reservoir and production analysis, which falls within applicant’s field of endeavor (reservoir planning and management), and because modifying the Benhallam-Bardy combination to include Tawil’s features for eluding wherein the missing reserves comprise behind casing opportunities (BCOs) identified based upon a quality trust factor exceeding a quality trust factor threshold, and wherein the second machine learning model generates a plurality of realizations by parameterizing property values above and below values provided by the first machine learning model to produce a probabilistic map of scenario distribution and a stochastic remaining oil-in-place map, in the manner claimed, would serve the motivation of enhancing business performance and commercial viability of well-planning operations (Tawil at paragraph 0039); and further obvious because the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
As per claim 2, the Benhallam-Bardy-Tawil combination teaches the method of claim 1. Benhallam further teaches wherein the well site data comprises a set of log curves, production curves, core data, and Special Core Analysis (SCAL) data for each of the plurality of well sites (paragraph 0007, discussing that the computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify grid regions in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints; paragraph 0033, discussing that the computer system accesses petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site; paragraph 0070, discussing that a drained net pay (DNP) log may be created in each well using an algorithm that incorporates the most recent completion data together with a net pay log reflecting various petrophysical cutoffs (e.g. porosity, permeability, water saturation, etc.) [i.e., special core analysis data – as noted in the Specification at paragraph 0045: “Special Core Analysis Data (SCAL)” includes data such as “relative permeability, capillary pressure, wettability”]; paragraph 0071, discussing that the algorithm can also be customized to make sure the uncontacted pay intervals are consistent with the particular perforation strategy adopted in the field…In addition, the process of identifying these uncontacted pay intervals can be augmented with dynamic data sources. These can include recurrent log curves such as PNLs (Pulsed Neutron Logs) that probe the formation with neutrons and track water saturation at the time of the measurement…The platform described can combine these curves together and create a corresponding date log that tracks the date stamp for every interval point. The user can then use this combined PNL log to filter through the UNP (uncontacted net pay) log; paragraph 0099, discussing using zone-specific production type curves normalized by static variables such as permeability-thickness; paragraph 0110, discussing that the method includes accessing one or more portions of petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site. For example, the data accessing module may access petrophysical log data obtained at hydrocarbon extraction site; paragraphs 0068, 0083).
As per claim 3, the Benhallam-Bardy-Tawil combination teaches the method of claim 2. Benhallam further teaches comprising: identifying interventions applied at the plurality of well sites in the set of log curves, the production curves, the core data and the SCAL data (paragraph 0007, discussing that the computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify grid regions in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints; paragraph 0033, discussing that the computer system accesses petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site; paragraph 0110, discussing that the method includes accessing one or more portions of petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site. For example, the data accessing module may access petrophysical log data obtained at hydrocarbon extraction site; paragraph 0070, discussing that a drained net pay (DNP) log may be created in each well using an algorithm that incorporates the most recent completion data together with a net pay log reflecting various petrophysical cutoffs (e.g. porosity, permeability, water saturation, etc.) [i.e., special core analysis data – as noted in the Specification at paragraph 0045: “Special Core Analysis Data (SCAL)” includes data such as “relative permeability, capillary pressure, wettability”]; paragraph 0071, discussing that the algorithm can also be customized to make sure the uncontacted pay intervals are consistent with the particular perforation strategy adopted in the field…In addition, the process of identifying these uncontacted pay intervals can be augmented with dynamic data sources. These can include recurrent log curves such as PNLs (Pulsed Neutron Logs) that probe the formation with neutrons and track water saturation at the time of the measurement…The platform described can combine these curves together and create a corresponding date log that tracks the date stamp for every interval point. The user can then use this combined PNL log to filter through the UNP (uncontacted net pay) log; paragraph 0099, discussing using zone-specific production type curves normalized by static variables such as permeability-thickness; paragraphs 0068, 0083, 0092, 0128); and
generating predicted reservoir quality index for each well and pay zones within the plurality of well sites based on the set of log curves, the production curves, the core data and the SCAL data, and the plurality of intervention options (paragraph 0033, discussing that the computer system also accesses historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals that represent material remaining in hydrocarbon wells on the hydrocarbon site; paragraph 0034, discussing that the projected production results include initial production estimates and/or ultimate recovery estimates. The computer system calculates a level of geologic uncertainty relative to the forecasted production results and determined drainage, where the geologic uncertainty levels indicate levels of risk; paragraph 0057, discussing a fully automated platform that applies advanced computational algorithms and data mining techniques on multi-disciplinary datasets to identify various remaining, feasible, and actionable field development opportunities. These include recompletion behind-pipe opportunities, vertical new drill locations, sidetrack opportunities, and optimal deviated/horizontal targets. The platform can also be used to identify custom types of opportunities such as reactivation opportunities; paragraph 0070, discussing that a drained net pay (DNP) log may be created in each well using an algorithm that incorporates the most recent completion data together with a net pay log reflecting various petrophysical cutoffs (e.g. porosity, permeability, water saturation, etc.). The algorithm tracks each net pay interval that is in direct or indirect communication with existing perforations. This tracking can also be customized to account for flow barriers (i.e. baffles). The characteristic attributes of what constitutes a baffle layer are provided by the user. For example, a pay interval that is separated from an existing perforation by a baffle will not be tracked or considered drained by the algorithm. The remaining pay that is not part of the DNP intervals is classified as uncontacted net pay (UNP); paragraph 0071, discussing that the algorithm can also be customized to make sure the uncontacted pay intervals are consistent with the particular perforation strategy adopted in the field. In addition, the process of identifying these uncontacted pay intervals can be augmented with dynamic data sources. These can include recurrent log curves such as PNLs (Pulsed Neutron Logs) that probe the formation with neutrons and track water saturation at the time of the measurement. Since sequential PNL log runs do not necessarily cover the same depth intervals, the platform described herein can combine these curves together and create a corresponding date log that tracks the date stamp for every interval point; paragraph 0074, discussing that small DIs (drainage index) reflect areas where only thin sand layers have been accessed or drained, and therefore have more oil remaining in either overlying or underlying sand packages; paragraph 0110, discussing that the data accessing module may also access historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals. These uncontacted net pay intervals represent material remaining in hydrocarbon wells on the hydrocarbon site; paragraphs 0068, 0083).
As per claim 6, the Benhallam-Bardy-Tawil combination teaches the method of claim 1. Benhallam further teaches wherein the candidate wells are selected from existing well sites in the reservoir (paragraph 0010, discussing that the computer system also includes a drainage analyzer configured to identify zones of the hydrocarbon extraction site that include drained portions that have been drained by existing wells on the site, along with a 3D map generator configured to generate a relative probability of success (RPOS) 3D map that ranks the identified zones of the site according to zone-mappable attributes associated with productive hydrocarbon wells; paragraph 0069, discussing that behind-pipe opportunities refer to target intervals that contain unswept oil in existing wells, which require additional recompletions for production. The identification of behind-pipe opportunities is accomplished through a multi-step workflow that integrates both geologic and engineering data, and that starts with the identification of uncontacted pay intervals; paragraph 0110, discussing accessing one or more portions of petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site. For example, the data accessing module may access petrophysical log data obtained at a hydrocarbon extraction site. The geological map generator may generate a geological map based on this petrophysical log data. The data accessing module may also access historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals. These uncontacted net pay intervals represent material remaining in hydrocarbon wells on the hydrocarbon site. As noted above, many wells are initially mined for a period of time, and when mining becomes economically unfeasible, the mining equipment is moved to more profitable wells. Thus, existing wells may still have uncontacted material in them; paragraph 0088).
As per claim 7, the Benhallam-Bardy-Tawil combination teaches the method of claim 1. Benhallam further teaches wherein the candidate wells are new well sites in the reservoir (paragraph 0007, discussing that a computer system identifies new vertical drill target opportunities. The computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify grid regions in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints. The computer system then generates a relative probability of success (RPOS) mapping for each zone that ranks the identified regions according to zone-mappable attributes associated with productive hydrocarbon wells, and further forecasts, for each new drill location, a potential production rate for one or more target zones; paragraph 0035, discussing that a computer system identifies new vertical drill target opportunities. The computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify well placement grid cells in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints; paragraph 0102).
Claims 8 and 15 recite substantially similar limitations that stand rejected via the art citations and rationale applied to claim 1, as discussed above. Further, as per claim 8 the Benhallam-Bardy-Tawil combination teaches a computer program product comprising: a non-transitory computer-readable storage media having program code stored thereon (Benhallam, paragraph 0040: “Embodiments of the present invention may comprise or utilize a special-purpose or general-purpose computer system that includes computer hardware, such as, for example, one or more processors and system memory, as discussed in greater detail below. Embodiments within the scope of the present invention also include physical and other computer-readable media for carrying or storing computer-executable instructions and/or data structures. Such computer-readable media can be any available media that can be accessed by a general-purpose or special-purpose computer system. Computer-readable media that store computer-executable instructions and/or data structures are computer storage media. Computer-readable media that carry computer-executable instructions and/or data structures are transmission media. Thus, by way of example, and not limitation, embodiments of the invention can comprise at least two distinctly different kinds of computer-readable media: computer storage media and transmission media.”). As per claim 15, the Benhallam-Bardy-Tawil combination teaches a system comprising: a computer processor; memory; and instructions stored in the memory and executable by the computer processor to cause the computer processor to perform operations (Benhallam, paragraph 0040: “Embodiments of the present invention may comprise or utilize a special-purpose or general-purpose computer system that includes computer hardware, such as, for example, one or more processors and system memory, as discussed in greater detail below. Embodiments within the scope of the present invention also include physical and other computer-readable media for carrying or storing computer-executable instructions and/or data structures. Such computer-readable media can be any available media that can be accessed by a general-purpose or special-purpose computer system. Computer-readable media that store computer-executable instructions and/or data structures are computer storage media. Computer-readable media that carry computer-executable instructions and/or data structures are transmission media. Thus, by way of example, and not limitation, embodiments of the invention can comprise at least two distinctly different kinds of computer-readable media: computer storage media and transmission media.”).
Claims 9 and 16 recite substantially similar limitations that stand rejected via the art citations and rationale applied to claim 2, as discussed above. Further, as per claims 9 and 16 the Benhallam-Bardy-Tawil combination teaches wherein the well site data comprises a set of production curves for each of the well sites (Benhallam, paragraph 0007, discussing that the computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify grid regions in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints; paragraph 0033, discussing that the computer system accesses petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site; paragraph 0110, discussing that the method includes accessing one or more portions of petrophysical log data obtained at a hydrocarbon extraction site to generate a geological map of the site. For example, the data accessing module may access petrophysical log data obtained at hydrocarbon extraction site; paragraph 0071, discussing that the algorithm can also be customized to make sure the uncontacted pay intervals are consistent with the particular perforation strategy adopted in the field…In addition, the process of identifying these uncontacted pay intervals can be augmented with dynamic data sources. These can include recurrent log curves such as PNLs (Pulsed Neutron Logs) that probe the formation with neutrons and track water saturation at the time of the measurement…The platform described can combine these curves together and create a corresponding date log that tracks the date stamp for every interval point. The user can then use this combined PNL log to filter through the UNP (uncontacted net pay) log; paragraph 0099, discussing using zone-specific production type curves normalized by static variables such as permeability-thickness).
Claims 10 and 17 recite substantially similar limitations that stand rejected via the art citations and rationale applied to claim 3, as discussed above. Further, as per claims 10 and 17 the Benhallam-Bardy-Tawil combination teaches generating predicted curves for the well sites based on the set of production curves and the interventions that were identified (Benhallam, paragraph 0007, discussing that the computer system accesses geological, petrophysical or engineering data related to a hydrocarbon extraction site, and analyzes the accessed data to identify grid regions in the hydrocarbon extraction site that are fit for placing new wells according to well placement constraints; paragraph 0034, discussing that the computer system forecasts, using statistical characterization methods and machine learning algorithms, projected production results for recompletion opportunities at the hydrocarbon site. The projected production results include initial production estimates and/or ultimate recovery estimates; paragraph 0057, discussing a fully automated platform that applies advanced computational algorithms and data mining techniques on multi-disciplinary datasets to identify various remaining, feasible, and actionable field development opportunities. These include recompletion behind-pipe opportunities, vertical new drill locations, sidetrack opportunities, and optimal deviated/horizontal targets. The platform can also be used to identify custom types of opportunities such as reactivation opportunities; paragraph 0070, discussing that a drained net pay (DNP) log may be created in each well using an algorithm that incorporates the most recent completion data together with a net pay log reflecting various petrophysical cutoffs (e.g. porosity, permeability, water saturation, etc.). The algorithm tracks each net pay interval that is in direct or indirect communication with existing perforations. This tracking can also be customized to account for flow barriers (i.e. baffles). The characteristic attributes of what constitutes a baffle layer are provided by the user. For example, a pay interval that is separated from an existing perforation by a baffle will not be tracked or considered drained by the algorithm. The remaining pay that is not part of the DNP intervals is classified as uncontacted net pay (UNP); paragraph 0071, discussing that the algorithm can also be customized to make sure the uncontacted pay intervals are consistent with the particular perforation strategy adopted in the field. In addition, the process of identifying these uncontacted pay intervals can be augmented with dynamic data sources. These can include recurrent log curves such as PNLs (Pulsed Neutron Logs) that probe the formation with neutrons and track water saturation at the time of the measurement. Since sequential PNL log runs do not necessarily cover the same depth intervals, the platform described herein can combine these curves together and create a corresponding date log that tracks the date stamp for every interval point; paragraphs 0056, 0074, 0083).
Claim 13 recites substantially similar limitations that stand rejected via the art citations and rationale applied to claim 6, as discussed above.
Claim 14 recites substantially similar limitations that stand rejected via the art citations and rationale applied to claim 7, as discussed above.
Claim 20 recites substantially similar limitations that stand rejected via the art citations and rationale applied to claims 6 and 7, as discussed above.
32. Claims 4-5, 11-12, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Benhallam in view of Bardy, in view of Tawil, in further view of Graf et al., Pub. No.: US 2009/0020284 A1, [hereinafter Graf].
As per claim 4, the Benhallam-Bardy-Tawil combination teaches the method of claim 3. Benhallam further teaches comprising, prior to implementing the intervention, interpolating the property values between the plurality of well sites to identify missing reserves in between the plurality of well sites and specific pay zone in time using the production curves and reservoir quality indicators of well sites (paragraph 0033, discussing that the computer system also accesses historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals that represent material remaining in hydrocarbon wells on the hydrocarbon site; paragraph 0034, discussing that the computer system forecasts, using statistical characterization methods and machine learning algorithms, projected production results for recompletion opportunities at the hydrocarbon site. The projected production results include initial production estimates and/or ultimate recovery estimates. The computer system calculates a level of geologic uncertainty relative to the forecasted production results and determined drainage, where the geologic uncertainty levels indicate levels of risk; paragraph 0057, discussing identifying various remaining, feasible, and actionable field development opportunities. These include recompletion behind-pipe opportunities, vertical new drill locations, sidetrack opportunities, and optimal deviated/horizontal targets; paragraph 0070, discussing that a drained net pay (DNP) log may be created in each well using an algorithm that incorporates the most recent completion data together with a net pay log reflecting various petrophysical cutoffs (e.g. porosity, permeability, water saturation, etc.). The algorithm tracks each net pay interval that is in direct or indirect communication with existing perforations. This tracking can also be customized to account for flow barriers (i.e. baffles). The characteristic attributes of what constitutes a baffle layer are provided by the user. For example, a pay interval that is separated from an existing perforation by a baffle will not be tracked or considered drained by the algorithm. The remaining pay that is not part of the DNP intervals is classified as uncontacted net pay (UNP); paragraph 0074, discussing that small DIs (drainage index) reflect areas where only thin sand layers have been accessed or drained, and therefore have more oil remaining in either overlying or underlying sand packages; paragraph 0110, discussing that the data accessing module may also access historical completion data for the hydrocarbon extraction site to identify uncontacted net pay intervals. These uncontacted net pay intervals represent material remaining in hydrocarbon wells on the hydrocarbon site. As noted above, many wells are initially mined for a period of time, and when mining becomes economically unfeasible, the mining equipment is moved to more profitable wells. Thus, existing wells may still have uncontacted material in them; paragraph 0067, 0111).
Benhallam does not explicitly teach using reservoir quality indicators of similar well sites. However, Graf in the analogous art of oilfield operation management teaches this concept. Graf teaches:
using reservoir quality indicators of similar well sites (paragraph 0012, discussing that the data from neighboring wellbores or wellbores with similar conditions or equipment may be used to predict how a well will perform; paragraph 0063, discussing that data plots are examples of static data plots that may be generated by the data acquisition tools, respectively. Static data plot is a seismic two-way response time. Static plot is core sample data measured from a core sample of the formation. Static data plot is a logging trace…Data plot is a dynamic data plot of the fluid flow rate over time. Other data may also be collected, such as historical data, user inputs, economic information, other measurement data, and other parameters of interest; paragraph 0096, discussing that multi-dimensional cross-plots and blind tests may be performed to control the quality of the back-populated oilfield data sets. Moreover, probability information of both the originally populated data fields and the back-populated data fields may also be analyzed to identify outliers that may indicate inconsistency of members in the oilfield data sets. Accordingly, validation ranges for data fields may be established against which originally populated data fields and/or back-populated data fields may be validated. In one or more embodiments of the invention, the back-populated oilfield data sets may be a stochastic database including these various probability and validation information for the corresponding oilfield entities; paragraph 0105, discussing that important information for each particular oilfield operation may be indicated by certain data fields in the oilfield data set. These critical data fields are key performance indicators (KPIs) for the respective oilfield operation. For example, reservoir-level parameters such as bubble point pressure, compressibility, formation volume factor, initial pressure, gas oil ratio (GOR), permeability (K), gas cap volume to oil volume ratio, oil thickness, viscosity, gravity, porosity, and water saturation are considered KPIs in identifying candidates for waterflooding operation from a large number of reservoirs. In one or more embodiments of the invention, a second artificial neural network may be generated for the oilfield data sets associated with the KPIs . In one or more embodiments of the invention, the second artificial neural network includes all the identified KPIs as outputs such that statistical relationships between these KPIs and other data fields in the oilfield data sets are identified; paragraph 0107, discussing that the map represents the "log m-ratio" parameter of the KPIs for waterflooding operation…The cross-hatched pattern of each hexagonal cell represents the parameter value of corresponding reservoirs placed at the location based on the SOM algorithm. As is expected, reservoirs within a cluster has similar parameter values while reservoirs with dissimilar parameter values tend to be in separate clusters. In one or more embodiments of the invention, the clusters may be generated automatically by the SOM algorithm. In one or more embodiments of the invention, the automatic cluster generation by the SOM algorithm may be guided by user inputs. For example, the total number of clusters may be determined or otherwise constrained by a user input. In one or more embodiments of the invention, the clusters may be generated manually by visually analyzing the SOM; paragraph 0108, discussing that oilfield entities (e.g., reservoirs) corresponding to these SOM locations of each cluster tend to be similar in behavior with respect to the KPIs and the relationship of KPIs to other data fields of the oilfield data sets; paragraphs 0095, 0102).
The Benhallam-Bardy-Tawil combination describes features related to wellbore planning and implementing hydrocarbon production opportunities. Graf relates to techniques for performing oilfield operations relating to subterranean formations having reservoirs. Therefore they are deemed to be analogous as they both are directed towards solutions for wellbore operations management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Benhallam-Bardy-Tawil combination with Graf because the references are analogous art because they are both directed to solutions for oilfield reservoir and production analysis, which falls within applicant’s field of endeavor (reservoir planning and management), and because modifying the Benhallam-Bardy-Tawil combination to include Graf’s feature for using reservoir quality indicators of similar well sites, in the manner claimed, would serve the motivation of modeling oilfield operations efficiently (Graf at paragraph 0102); and further obvious because the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
As per claim 5, the Benhallam-Bardy-Tawil combination teaches the method of claim 2. Although not explicitly taught by the Benhallam-Bardy-Tawil combination. Graf in the analogous art of oilfield operation management teaches comprising: generating vector representations of the plurality of well sites (paragraph 0095, discussing that similarities in the oilfield data sets among the collection of oilfield entities (e.g., a large number of reservoirs) may be displayed using a Self-Organizing Map (SOM). As is known in the art, a self-organizing map is a type of artificial neural network typically presented as discretized maps of training data rendered in color according to a color gradient bar, which maps data values to various colors…Each location is associated with a position in a map and a weight vector of the same dimension as the input data vectors of the training data…The first artificial neural network described may be a SOM and the input vectors are oilfield data sets for the oilfield entities involved in training the network where the dimension of the input vector is the number of data fields of the oilfield data sets. Each data field of the oilfield data sets may be represented as a map of the SOM where a vector (i.e., an oilfield data set of an oilfield entity) from data space (i.e., oilfield data sets of the collection of oilfield entities) is placed onto a map location with the weight vector closest to the vector taken from data space. Typically for a large collection of training data, multiple vectors sufficiently close to a weight vector may all be placed at a same location. For example, sufficiently similar reservoir-level data sets for multiple reservoirs may be placed at a single location of the SOM); and
determining similarities between the plurality of well sites prior to the intervention (paragraph 0012, discussing that the data from neighboring wellbores or wellbores with similar conditions or equipment may be used to predict how a well will perform; paragraph 0095, discussing that similarities in the oilfield data sets among the collection of oilfield entities (e.g., a large number of reservoirs) may be displayed using a Self-Organizing Map (SOM). As is known in the art, a self-organizing map is a type of artificial neural network typically presented as discretized maps of training data rendered in color according to a color gradient bar, which maps data values to various colors…Each location is associated with a position in a map and a weight vector of the same dimension as the input data vectors of the training data…The first artificial neural network described may be a SOM and the input vectors are oilfield data sets for the oilfield entities involved in training the network where the dimension of the input vector is the number of data fields of the oilfield data sets. Each data field of the oilfield data sets may be represented as a map of the SOM where a vector (i.e., an oilfield data set of an oilfield entity) from data space (i.e., oilfield data sets of the collection of oilfield entities) is placed onto a map location with the weight vector closest to the vector taken from data space. Typically for a large collection of training data, multiple vectors sufficiently close to a weight vector may all be placed at a same location. For example, sufficiently similar reservoir-level data sets for multiple reservoirs may be placed at a single location of the SOM);
The Benhallam-Bardy-Tawil combination describes features related to wellbore planning and implementing hydrocarbon production opportunities. Graf relates to techniques for performing oilfield operations relating to subterranean formations having reservoirs. Therefore they are deemed to be analogous as they both are directed towards solutions for wellbore operations management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Benhallam-Bardy-Tawil combination with Graf because the references are analogous art because they are both directed to solutions for oilfield reservoir and production analysis, which falls within applicant’s field of endeavor (reservoir planning and management), and because modifying the Benhallam-Bardy-Tawil combination to include Graf’s features for generating vector representations of the plurality of well sites and determining similarities between the plurality of well sites prior to the intervention, in the manner claimed, would serve the motivation of modeling oilfield operations efficiently (Graf at paragraph 0102); and further obvious because the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Claims 11 and 18 recite substantially similar limitations that stand rejected via the art citations and rationale applied to claim 4, as discussed above. Further, as per claim 11, the Benhallam-Bardy-Tawil-Graf combination teaches wherein the method further comprises: extrapolating each of the production curves in time prior to the interventions using the production curves of similar well sites (Graf, paragraph 0012, discussing that the data from neighboring wellbores or wellbores with similar conditions or equipment may be used to predict how a well will perform; paragraph 0030, discussing an exemplary simulation decline curve of fluid flowing through the subterranean formation; paragraph 0048, discussing that the collected data may be used to perform analysis, such as modeling operations. For example, the seismic data output may be used to perform geological, geophysical, reservoir engineering, and/or production simulations. The reservoir, wellbore, surface and/or process data may be used to perform reservoir, wellbore, or other production simulations; paragraph 0059, discussing that the production decline curve typically provides the production rate Q as a function of time t; paragraph 0063, discussing that data plots are examples of static data plots that may be generated by the data acquisition tools, respectively. Static data plot is a seismic two-way response time. Static plot is core sample data measured from a core sample of the formation. Static data plot is a logging trace…Data plot is a dynamic data plot of the fluid flow rate over time. Other data may also be collected, such as historical data, user inputs, economic information, other measurement data, and other parameters of interest; paragraph 0096, discussing that multi-dimensional cross-plots and blind tests may be performed to control the quality of the back-populated oilfield data sets. Moreover, probability information of both the originally populated data fields and the back-populated data fields may also be analyzed to identify outliers that may indicate inconsistency of members in the oilfield data sets. Accordingly, validation ranges for data fields may be established against which originally populated data fields and/or back-populated data fields may be validated. In one or more embodiments of the invention, the back-populated oilfield data sets may be a stochastic database including these various probability and validation information for the corresponding oilfield entities; paragraph 0108, discussing that oilfield entities (e.g., reservoirs) corresponding to these SOM locations of each cluster tend to be similar in behavior with respect to the KPIs and the relationship of KPIs to other data fields of the oilfield data sets; paragraphs 0057, 0105, 0107).
The Benhallam-Bardy-Tawil combination describes features related to wellbore planning and implementing hydrocarbon production opportunities. Graf relates to techniques for performing oilfield operations relating to subterranean formations having reservoirs. Therefore they are deemed to be analogous as they both are directed towards solutions for wellbore operations management. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Benhallam-Bardy-Tawil combination with Graf because the references are analogous art because they are both directed to solutions for oilfield reservoir and production analysis, which falls within applicant’s field of endeavor (reservoir planning and management), and because modifying the Benhallam-Bardy-Tawil combination to include Graf’s feature for extrapolating each of the production curves in time prior to the interventions using the production curves of similar well sites, in the manner claimed, would serve the motivation of modeling oilfield operations efficiently (Graf at paragraph 0102); and further obvious because the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable.
Claims 12 and 19 recite substantially similar limitations that stand rejected via the art citations and rationale applied to claim 5, as discussed above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Mustapha et al., Patent No.: US 10,895,131 B2 – describes an automated probabilistic workflow that optimizes well placement using probability maps based on reservoir and simulation opportunity indexes. This probability map approach may be used to effectively unify existing reservoir model realizations into a single or combined probability map by establishing thresholds for selected physical parameters and reservoir characteristics.
Darabi, Hamed, et al. "Augmented AI framework for well performance prediction and opportunity identification in unconventional reservoirs." International Petroleum Technology Conference. IPTC, 2020 – describes that many important business decisions and planning in unconventional reservoirs rely on a reliable forecast on well performance.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DARLENE GARCIA-GUERRA whose telephone number is (571) 270-3339. The examiner can normally be reached M-F 7:30a.m.-5:00p.m. EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Brian M. Epstein can be reached on (571) 270-5389. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Darlene Garcia-Guerra/
Primary Examiner, Art Unit 3625
Prosecution Insights